Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    put to work or on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     by
    0.67
    d
    0.53
    جع
    0.49
    AT
    0.48
    SwapChain
    0.48
    2
    0.46
    AC
    0.46
    ة
    0.46
    by
    0.45
    and
    0.45
    POSITIVE LOGITS
     put
    1.25
     puts
    1.08
     putting
    1.07
    Put
    1.05
     PUT
    0.99
    put
    0.98
    Putting
    0.97
     Put
    0.97
    putting
    0.96
     Putting
    0.93
    Act Density 0.035%

    No Known Activations